2M+ Downloads · 9K+ Stars
More than two million downloads, and over nine thousand stars on the repository.
MULTI-AGENT FRAMEWORKPYTHON AND JAVASCRIPTMIT LICENSED
Your application, or the chat
Write the job.
Ship the agent.
PraisonAI researches, plans, and carries out the work in the program you already ship. The instruction, the memory, the tools, the check, and which agent runs next are in that same call.
A developer calls an Agent, an Agent Team, or an Agent Flow from Agents. A person writes in the chat on the bot.
FROM ONE AGENTTO A WORKFORCE
01
Give agents a purpose.
Connect models and tools to turn an idea into an agent that can act.
02
Let them work together.
Build multi-agent workflows for research, planning and execution.
03
Keep what matters.
Bring memory and your own knowledge into the workflow with RAG.
Get started
One command.
This installs PraisonAI. When it finishes, run praisonai setup to add a provider key.
curl -fsSL https://raw.githubusercontent.com/MervinPraison/PraisonAI/main/install.sh | shTHE INSTALLERTHEN PRAISONAI SETUP
Advanced installs
- Python
pip install praisonaiagents- JavaScript
npm install praisonai- YAML
pip install praisonai praisonai agents.yaml- Key by hand
export OPENAI_API_KEY="your-key"
The first job
Research, then a finished table.
The repository opens on this agent. It takes a question, does the research, and returns a table. This is the first job. A larger one is an Agent Team or an Agent Flow.
- 01One instruction
Tell the agent it is a senior analyst.
- 02One question
Ask for the research, and for a table back.
- 03The work
A finished table, ready for the next draft or the next agent.
from praisonai import Agent
agent = Agent(instructions="You are a senior data analyst.")
agent.start("Analyze the top 3 tech trends of 2026 and format as a markdown table.")MEET YOUR FIRST AGENTUNDER A MINUTE
For people
A 24/7 agent.
An agent can answer in the chat people already use, and a scheduler can keep the job running. The dashboard stays on your machine.
- 01Four chats
Telegram, Discord, Slack, and WhatsApp. Add a channel from the dashboard.
- 02Memory and knowledge
A support reply can use what the agent remembers and what it has read.
- 03On a schedule
An agent scheduler runs the job on a clock.
Five short courses
Agent University.
Each course teaches one idea. The example is on the page, and you run the agent yourself. No account is required.
- 01Agents
Give one agent a job, check the answer, then run it on your computer.
- 02AgentFlow
Pass one job through two steps, a choice, parallel work, and a loop.
- 03RAG
Find the right section of a note, then answer from that section.
- 04Memory
Save a fact about a person, recall it, and keep it apart from a note.
- 05Skills
Load a folder of instructions only when the job matches.
PraisonAI is MIT licensed, and you run it on your own machine. A company that wants help adopting it can book a discovery call.